© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13214
    Prev
    Next
    INDEX
    Explanations

    variations of the verb 'take'

    oai_token-act-pair · gemini-2.0-flash

    take

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.70
    EndInit
    -0.69
    ResumeLayout
    -0.69
     resourceCulture
    -0.67
    ddots
    -0.65
     considérons
    -0.64
     ModelExpression
    -0.63
    AndEndTag
    -0.63
     contextLoads
    -0.63
     للمعارف
    -0.63
    POSITIVE LOGITS
     Sociales
    0.50
    וך
    0.48
    Izvori
    0.45
    ссора
    0.43
     to
    0.40
    uzu
    0.39
    extends
    0.37
    بینی
    0.37
    rão
    0.36
    netty
    0.36
    Activations Density 0.575%

    No Known Activations